250 000 kr
166 hours
1 month
Manuscript on pre-print server
Produce guidelines
if we aggregate (takes means of) of the scaled or unscaled variabel:
Scaling = Linear range scaling, usually reducing the range of the variable by using one or two reference value
Truncating = Cutting of value above or below a given threshold. In our case, making the metrices bound between 0 and 1. Truncation is also a type of scaling.
Re-scaling = not used, but often used as a synonym to normalisation.
Normalising = a combination of scaling, followed by truncating (if needed). This lead to a non-linear transformation of the original variable and returns indicators that share the same scale.
Non-linear scaling: Scaling functions like truncation, sigmoid, exponential or break-point types.
condition estimates (bottom) or actual measurements (top)
| ## Commutativty |
| ## Early scaling |
| leads to cummutativity |
| ::: {.cell layout-align=“left”} ::: {.cell-output-display} |
{=html} <div class="grViz html-widget html-fill-item-overflow-hidden html-fill-item" id="htmlwidget-7569f809769a2ede7346" style="width:672px;height:576px;"></div> <script type="application/json" data-for="htmlwidget-7569f809769a2ede7346">{"x":{"diagram":"digraph{\n \n \n graph [\n compound = true, \n nodesep = .8, \n ranksep = .8,\n color = crimson, \n rankdir = LR\n ]\n\n \n node [\n fontname = Helvetica, \n fontcolor = darkslategray,\n shape = rectangle, \n fixedsize = true, \n width = 1,\n color = darkslategray\n ]\n \n \n edge [\n color = black\n ]\n \n# Orange part --------------------------\n\n subgraph clusterTop {\n graph[color = orange]\n \n subgraph cluster0 {\n graph[color = green]\n peripheries=0;\n \n subgraph cluster0_1 {\n label=\"EA-1\";\n labeljust=l;\n peripheries=1;\n V2_EA1[label = \"Value = 5\nRef. = 25\", color = orange, style = filled, fontcolor = white]\n V1_EA1[label = \"Value = 5\nRef. = 10\", color = blue, style = filled, fontcolor = white]\n I1_EA1[label = \" .5\", color = blue, style = filled, fontcolor = white]\n I2_EA1[label = \" .2\", color = orange, style = filled, fontcolor = white]\n X_EA1[label = \" .35\", color = grey, style = filled]\n V1_EA1 -> I1_EA1 -> X_EA1\n V2_EA1 -> I2_EA1 -> X_EA1\n \n }\n \n subgraph cluster0_2 {\n label=\"EA-2\";\n labeljust=l;\n peripheries=1;\n V2_EA2[label = \"Value = 1\nRef. = 10\", color = orange, style = filled, fontcolor = white]\n V1_EA2[label = \"Value = 1\nRef. = 4\", color = blue, style = filled, fontcolor = white]\n I1_EA2[label = \" .25\", color = blue, style = filled, fontcolor = white]\n I2_EA2[label = \" .1\", color = orange, style = filled, fontcolor = white]\n X_EA2[label = \" .175\", color = grey, style = filled]\n V1_EA2 -> I1_EA2 -> X_EA2\n V2_EA2 -> I2_EA2 -> X_EA2\n }\n }\nX[label = \".2625\", color = grey, style = filled]\nX_EA1 -> X\nX_EA2 -> X\n\n}\n\n\n \n \n\n}","config":{"engine":"dot","options":null}},"evals":[],"jsHooks":[]}</script> |
| ::: ::: |
leads to cummutativity
we can aggregate the actual measurements. When would this make sense to do?
notes from Bård
Reference values serve two purposes
As a consequence, an index of rescaled indicators summarizes negative deviations from the reference state over a large set of indicators.
Unscaled states above the reference value are not recognized as being better than the reference state.
Rescaling is useful for making indeces, but why use it for individual indicators? [answer: it depends if we want to aggregate ‘condition estimates’ of actuall measurements]